50% token reduction for agents is huge if it holds up in real production workloads. I wonder how this generalizes beyond their benchmarks.
AGENTS
-
Chrome MCP enables browser automation for Microsoft Foundry integration
By
–
Testing a new feature for Microsoft Foundry support in @openclaw
. Their website is a jungle, I used to make screenshots so codex can guide me through it, but now Chrome has an MCP so codex can simply connect and drive my browser session and do all of that for me. The human is no -
GTR Framework Prevents AI Agents Getting Stuck in Reasoning Loops
By
–
How can we stop AI agents from getting 'stuck' in their own thoughts? Researchers from Tsinghua University, Tencent, and Peking University introduce GTR (Guided Thought Reinforcement). This novel framework uses an automated corrector to evaluate and refine an agent's reasoning
-
AI Scientist Paper Published in Nature, Advancing Automated Research
By
–
Still remember the experiment grind over New Year's break–really great to see this out in Nature today! AI automation of AI research is heating up fast, and I'm excited to see what becomes possible as models keep improving (see the figure below!) Sakana AI (@SakanaAILabs) The AI Scientist: Towards Fully Automated AI Research, Now Published in Nature Nature: nature.com/articles/s41586-0… Blog: sakana.ai/ai-scientist-natur… When we first introduced The AI Scientist, we shared an ambitious vision of an agent powered by foundation models capable of executing the entire machine learning research lifecycle. From inventing ideas and writing code to executing experiments and drafting the manuscript, the system demonstrated that end-to-end automation of the scientific process is possible. Soon after, we shared a historic update: the improved AI Scientist-v2 produced the first fully AI-generated paper to pass a rigorous human peer-review process. Today, we are happy to announce that “The AI Scientist: Towards Fully Automated AI Research,” our paper describing all of this work, along with fresh new insights, has been published in @Nature! This Nature publication consolidates these milestones and details the underlying foundation model orchestration. It also introduces our Automated Reviewer, which matches human review judgments and actually exceeds standard inter-human agreement. Crucially, by using this reviewer to grade papers generated by different foundation models, we discovered a clear scaling law of science. As the underlying foundation models improve, the quality of the generated scientific papers increases correspondingly. This implies that as compute costs decrease and model capabilities continue to exponentially increase, future versions of The AI Scientist will be substantially more capable. Building upon our previous open-source releases (github.com/SakanaAI/AI-Scien…), this open-access Nature publication comprehensively details our system's architecture, outlines several new scaling results, and discusses the promise and challenges of AI-generated science. This substantial milestone is the result of a close and fruitful collaboration between researchers at Sakana AI, the University of British Columbia (UBC) and the Vector Institute, and the University of Oxford. Congrats to the team! @_chris_lu_ @cong_ml @RobertTLange @_yutaroyamada @shengranhu @j_foerst @hardmaru @jeffclune — https://nitter.net/SakanaAILabs/status/2036840833690071450#m
→ View original post on X — @_yutaroyamada, 2026-03-26 13:38 UTC
-
First Autonomous AI Worker OpenClaw Launches with Funded Wallet
By
–
[ The first autonomous worker is coming online ] Setting up the first autonomous worker: OpenClaw, running on a dedicated machine with its own accounts and a $AGIALPHA-funded wallet. It will listen to AGIJobManager, autonomously apply to AGI Jobs, execute them, and submit
-
Cohere Launches First Speech-to-Text Model for Enterprise
By
–
This is Cohere’s first speech-to-text model release and a huge step towards our goal of delivering enterprise speech intelligence into North, Cohere’s agentic AI orchestration platform.
-
From Human-in-the-Loop to Human-Out-of-the-Loop AI Coding
By
–
We've gone from the 2025 of human-in-the-loop and the vibe coding to being in 2026 with Karpathy feeling like the bottleneck that's limiting AI work, and with new concepts like human-out-of-the-loop and blind coding.
-
OpenAI Backs Isara: AI Agents Startup Raises $94M
By
–
OpenAI is backing Isara, a new startup founded by two 23-year-old AI researchers that coordinates thousands of AI agents to solve complex problems, like using ~2,000 agents to forecast gold prices. The company just raised $94M at a $650M valuation and plans to sell predictive
-
Genspark Launches Hands-Free Realtime Voice AI for Commuters
By
–
🚗 Your commute just got a major upgrade.
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 26 mars 2026
Introducing Genspark Realtime Voice — the fully hands-free AI assistant that works while you drive.
What it can do:
→ Check your schedule
→ Send emails & messages
→ Look things up on the web
→ Build a commute playlist
→ Generate… pic.twitter.com/BNAOj0E6uRYour commute just got a major upgrade. Introducing Genspark Realtime Voice — the fully hands-free AI assistant that works while you drive. What it can do:
→ Check your schedule
→ Send emails & messages
→ Look things up on the web
→ Build a commute playlist
→ Generate -
AI Meeting Assistant Turns Calls Into Notes Without Recording
By
–
Stop wasting time “re-watching” meetings you already sat through. There’s a new AI meeting assistant that quietly sits on your Mac, listens in real time, and turns every call into clean notes, decisions, and action items—without even recording the meeting. If you live in